ip_conntrack_core.c

Linux Kernel 2.6.9 for OMAP1710

		/* choose the the oldest expectation to evict */
		list_for_each_entry(old, &related_to->sibling_list, 
		                                      expected_list)
			if (old->sibling == NULL)
				break;

		/* We cannot fail since related_to->expecting is the number
		 * of unconfirmed expectations */
		IP_NF_ASSERT(old && old->sibling == NULL);

		/* newnat14 does not reuse the real allocated memory
		 * structures but rather unexpects the old and
		 * allocates a new.  unexpect_related will decrement
		 * related_to->expecting. 
		 */
		unexpect_related(old);
		ret = -EPERM;
	} else if (LIST_FIND(&ip_conntrack_expect_list, expect_clash,
			     struct ip_conntrack_expect *, &expect->tuple, 
			     &expect->mask)) {
		WRITE_UNLOCK(&ip_conntrack_lock);
		DEBUGP("expect_related: busy!\n");

		kmem_cache_free(ip_conntrack_expect_cachep, expect);
		return -EBUSY;
	}

out:	ip_conntrack_expect_insert(expect, related_to);

	WRITE_UNLOCK(&ip_conntrack_lock);

	CONNTRACK_STAT_INC(expect_create);

	return ret;
}

/* Change tuple in an existing expectation */
int ip_conntrack_change_expect(struct ip_conntrack_expect *expect,
			       struct ip_conntrack_tuple *newtuple)
{
	int ret;

	MUST_BE_READ_LOCKED(&ip_conntrack_lock);
	WRITE_LOCK(&ip_conntrack_expect_tuple_lock);

	DEBUGP("change_expect:\n");
	DEBUGP("exp tuple: "); DUMP_TUPLE(&expect->tuple);
	DEBUGP("exp mask:  "); DUMP_TUPLE(&expect->mask);
	DEBUGP("newtuple:  "); DUMP_TUPLE(newtuple);
	if (expect->ct_tuple.dst.protonum == 0) {
		/* Never seen before */
		DEBUGP("change expect: never seen before\n");
		if (!ip_ct_tuple_equal(&expect->tuple, newtuple) 
		    && LIST_FIND(&ip_conntrack_expect_list, expect_clash,
			         struct ip_conntrack_expect *, newtuple, &expect->mask)) {
			/* Force NAT to find an unused tuple */
			ret = -1;
		} else {
			memcpy(&expect->ct_tuple, &expect->tuple, sizeof(expect->tuple));
			memcpy(&expect->tuple, newtuple, sizeof(expect->tuple));
			ret = 0;
		}
	} else {
		/* Resent packet */
		DEBUGP("change expect: resent packet\n");
		if (ip_ct_tuple_equal(&expect->tuple, newtuple)) {
			ret = 0;
		} else {
			/* Force NAT to choose again the same port */
			ret = -1;
		}
	}
	WRITE_UNLOCK(&ip_conntrack_expect_tuple_lock);
	
	return ret;
}

/* Alter reply tuple (maybe alter helper).  If it's already taken,
   return 0 and don't do alteration. */
int ip_conntrack_alter_reply(struct ip_conntrack *conntrack,
			     const struct ip_conntrack_tuple *newreply)
{
	WRITE_LOCK(&ip_conntrack_lock);
	if (__ip_conntrack_find(newreply, conntrack)) {
		WRITE_UNLOCK(&ip_conntrack_lock);
		return 0;
	}
	/* Should be unconfirmed, so not in hash table yet */
	IP_NF_ASSERT(!is_confirmed(conntrack));

	DEBUGP("Altering reply tuple of %p to ", conntrack);
	DUMP_TUPLE(newreply);

	conntrack->tuplehash[IP_CT_DIR_REPLY].tuple = *newreply;
	if (!conntrack->master && list_empty(&conntrack->sibling_list))
		conntrack->helper = ip_ct_find_helper(newreply);
	WRITE_UNLOCK(&ip_conntrack_lock);

	return 1;
}

int ip_conntrack_helper_register(struct ip_conntrack_helper *me)
{
	WRITE_LOCK(&ip_conntrack_lock);
	list_prepend(&helpers, me);
	WRITE_UNLOCK(&ip_conntrack_lock);

	return 0;
}

static inline int unhelp(struct ip_conntrack_tuple_hash *i,
			 const struct ip_conntrack_helper *me)
{
	if (i->ctrack->helper == me) {
		/* Get rid of any expected. */
		remove_expectations(i->ctrack, 0);
		/* And *then* set helper to NULL */
		i->ctrack->helper = NULL;
	}
	return 0;
}

void ip_conntrack_helper_unregister(struct ip_conntrack_helper *me)
{
	unsigned int i;

	/* Need write lock here, to delete helper. */
	WRITE_LOCK(&ip_conntrack_lock);
	LIST_DELETE(&helpers, me);

	/* Get rid of expecteds, set helpers to NULL. */
	for (i = 0; i < ip_conntrack_htable_size; i++)
		LIST_FIND_W(&ip_conntrack_hash[i], unhelp,
			    struct ip_conntrack_tuple_hash *, me);
	WRITE_UNLOCK(&ip_conntrack_lock);

	/* Someone could be still looking at the helper in a bh. */
	synchronize_net();
}

static inline void ct_add_counters(struct ip_conntrack *ct,
				   enum ip_conntrack_info ctinfo,
				   const struct sk_buff *skb)
{
#ifdef CONFIG_IP_NF_CT_ACCT
	if (skb) {
		ct->counters[CTINFO2DIR(ctinfo)].packets++;
		ct->counters[CTINFO2DIR(ctinfo)].bytes += 
					ntohs(skb->nh.iph->tot_len);
	}
#endif
}

/* Refresh conntrack for this many jiffies and do accounting (if skb != NULL) */
void ip_ct_refresh_acct(struct ip_conntrack *ct, 
		        enum ip_conntrack_info ctinfo,
			const struct sk_buff *skb,
			unsigned long extra_jiffies)
{
	IP_NF_ASSERT(ct->timeout.data == (unsigned long)ct);

	/* If not in hash table, timer will not be active yet */
	if (!is_confirmed(ct)) {
		ct->timeout.expires = extra_jiffies;
		ct_add_counters(ct, ctinfo, skb);
	} else {
		WRITE_LOCK(&ip_conntrack_lock);
		/* Need del_timer for race avoidance (may already be dying). */
		if (del_timer(&ct->timeout)) {
			ct->timeout.expires = jiffies + extra_jiffies;
			add_timer(&ct->timeout);
		}
		ct_add_counters(ct, ctinfo, skb);
		WRITE_UNLOCK(&ip_conntrack_lock);
	}
}

int ip_ct_no_defrag;

/* Returns new sk_buff, or NULL */
struct sk_buff *
ip_ct_gather_frags(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;
#ifdef CONFIG_NETFILTER_DEBUG
	unsigned int olddebug = skb->nf_debug;
#endif

	if (unlikely(ip_ct_no_defrag)) {
		kfree_skb(skb);
		return NULL;
	}

	if (sk) {
		sock_hold(sk);
		skb_orphan(skb);
	}

	local_bh_disable(); 
	skb = ip_defrag(skb);
	local_bh_enable();

	if (!skb) {
		if (sk)
			sock_put(sk);
		return skb;
	}

	if (sk) {
		skb_set_owner_w(skb, sk);
		sock_put(sk);
	}

	ip_send_check(skb->nh.iph);
	skb->nfcache |= NFC_ALTERED;
#ifdef CONFIG_NETFILTER_DEBUG
	/* Packet path as if nothing had happened. */
	skb->nf_debug = olddebug;
#endif
	return skb;
}

/* Used by ipt_REJECT. */
static void ip_conntrack_attach(struct sk_buff *nskb, struct sk_buff *skb)
{
	struct ip_conntrack *ct;
	enum ip_conntrack_info ctinfo;

	/* This ICMP is in reverse direction to the packet which caused it */
	ct = ip_conntrack_get(skb, &ctinfo);
	
	if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL)
		ctinfo = IP_CT_RELATED + IP_CT_IS_REPLY;
	else
		ctinfo = IP_CT_RELATED;

	/* Attach to new skbuff, and increment count */
	nskb->nfct = &ct->ct_general;
	nskb->nfctinfo = ctinfo;
	nf_conntrack_get(nskb->nfct);
}

static inline int
do_kill(const struct ip_conntrack_tuple_hash *i,
	int (*kill)(const struct ip_conntrack *i, void *data),
	void *data)
{
	return kill(i->ctrack, data);
}

/* Bring out ya dead! */
static struct ip_conntrack_tuple_hash *
get_next_corpse(int (*kill)(const struct ip_conntrack *i, void *data),
		void *data, unsigned int *bucket)
{
	struct ip_conntrack_tuple_hash *h = NULL;

	READ_LOCK(&ip_conntrack_lock);
	for (; !h && *bucket < ip_conntrack_htable_size; (*bucket)++) {
		h = LIST_FIND(&ip_conntrack_hash[*bucket], do_kill,
			      struct ip_conntrack_tuple_hash *, kill, data);
	}
	if (h)
		atomic_inc(&h->ctrack->ct_general.use);
	READ_UNLOCK(&ip_conntrack_lock);

	return h;
}

void
ip_ct_selective_cleanup(int (*kill)(const struct ip_conntrack *i, void *data),
			void *data)
{
	struct ip_conntrack_tuple_hash *h;
	unsigned int bucket = 0;

	while ((h = get_next_corpse(kill, data, &bucket)) != NULL) {
		/* Time to push up daises... */
		if (del_timer(&h->ctrack->timeout))
			death_by_timeout((unsigned long)h->ctrack);
		/* ... else the timer will get him soon. */

		ip_conntrack_put(h->ctrack);
	}
}

/* Fast function for those who don't want to parse /proc (and I don't
   blame them). */
/* Reversing the socket's dst/src point of view gives us the reply
   mapping. */
static int
getorigdst(struct sock *sk, int optval, void __user *user, int *len)
{
	struct inet_opt *inet = inet_sk(sk);
	struct ip_conntrack_tuple_hash *h;
	struct ip_conntrack_tuple tuple;
	
	IP_CT_TUPLE_U_BLANK(&tuple);
	tuple.src.ip = inet->rcv_saddr;
	tuple.src.u.tcp.port = inet->sport;
	tuple.dst.ip = inet->daddr;
	tuple.dst.u.tcp.port = inet->dport;
	tuple.dst.protonum = IPPROTO_TCP;

	/* We only do TCP at the moment: is there a better way? */
	if (strcmp(sk->sk_prot->name, "TCP")) {
		DEBUGP("SO_ORIGINAL_DST: Not a TCP socket\n");
		return -ENOPROTOOPT;
	}

	if ((unsigned int) *len < sizeof(struct sockaddr_in)) {
		DEBUGP("SO_ORIGINAL_DST: len %u not %u\n",
		       *len, sizeof(struct sockaddr_in));
		return -EINVAL;
	}

	h = ip_conntrack_find_get(&tuple, NULL);
	if (h) {
		struct sockaddr_in sin;

		sin.sin_family = AF_INET;
		sin.sin_port = h->ctrack->tuplehash[IP_CT_DIR_ORIGINAL]
			.tuple.dst.u.tcp.port;
		sin.sin_addr.s_addr = h->ctrack->tuplehash[IP_CT_DIR_ORIGINAL]
			.tuple.dst.ip;

		DEBUGP("SO_ORIGINAL_DST: %u.%u.%u.%u %u\n",
		       NIPQUAD(sin.sin_addr.s_addr), ntohs(sin.sin_port));
		ip_conntrack_put(h->ctrack);
		if (copy_to_user(user, &sin, sizeof(sin)) != 0)
			return -EFAULT;
		else
			return 0;
	}
	DEBUGP("SO_ORIGINAL_DST: Can't find %u.%u.%u.%u/%u-%u.%u.%u.%u/%u.\n",
	       NIPQUAD(tuple.src.ip), ntohs(tuple.src.u.tcp.port),
	       NIPQUAD(tuple.dst.ip), ntohs(tuple.dst.u.tcp.port));
	return -ENOENT;
}

static struct nf_sockopt_ops so_getorigdst = {
	.pf		= PF_INET,
	.get_optmin	= SO_ORIGINAL_DST,
	.get_optmax	= SO_ORIGINAL_DST+1,
	.get		= &getorigdst,
};

static int kill_all(const struct ip_conntrack *i, void *data)
{
	return 1;
}

/* Mishearing the voices in his head, our hero wonders how he's
   supposed to kill the mall. */
void ip_conntrack_cleanup(void)
{
	ip_ct_attach = NULL;
	/* This makes sure all current packets have passed through
           netfilter framework.  Roll on, two-stage module
           delete... */
	synchronize_net();
 
 i_see_dead_people:
	ip_ct_selective_cleanup(kill_all, NULL);
	if (atomic_read(&ip_conntrack_count) != 0) {
		schedule();
		goto i_see_dead_people;
	}

	kmem_cache_destroy(ip_conntrack_cachep);
	kmem_cache_destroy(ip_conntrack_expect_cachep);
	vfree(ip_conntrack_hash);
	nf_unregister_sockopt(&so_getorigdst);
}

static int hashsize;
module_param(hashsize, int, 0400);

int __init ip_conntrack_init(void)
{
	unsigned int i;
	int ret;

	/* Idea from tcp.c: use 1/16384 of memory.  On i386: 32MB
	 * machine has 256 buckets.  >= 1GB machines have 8192 buckets. */
 	if (hashsize) {
 		ip_conntrack_htable_size = hashsize;
 	} else {
		ip_conntrack_htable_size
			= (((num_physpages << PAGE_SHIFT) / 16384)
			   / sizeof(struct list_head));
		if (num_physpages > (1024 * 1024 * 1024 / PAGE_SIZE))
			ip_conntrack_htable_size = 8192;
		if (ip_conntrack_htable_size < 16)
			ip_conntrack_htable_size = 16;
	}
	ip_conntrack_max = 8 * ip_conntrack_htable_size;

	printk("ip_conntrack version %s (%u buckets, %d max)"
	       " - %Zd bytes per conntrack\n", IP_CONNTRACK_VERSION,
	       ip_conntrack_htable_size, ip_conntrack_max,
	       sizeof(struct ip_conntrack));

	ret = nf_register_sockopt(&so_getorigdst);
	if (ret != 0) {
		printk(KERN_ERR "Unable to register netfilter socket option\n");
		return ret;
	}

	ip_conntrack_hash = vmalloc(sizeof(struct list_head)
				    * ip_conntrack_htable_size);
	if (!ip_conntrack_hash) {
		printk(KERN_ERR "Unable to create ip_conntrack_hash\n");
		goto err_unreg_sockopt;
	}

	ip_conntrack_cachep = kmem_cache_create("ip_conntrack",
	                                        sizeof(struct ip_conntrack), 0,
	                                        SLAB_HWCACHE_ALIGN, NULL, NULL);
	if (!ip_conntrack_cachep) {
		printk(KERN_ERR "Unable to create ip_conntrack slab cache\n");
		goto err_free_hash;
	}

	ip_conntrack_expect_cachep = kmem_cache_create("ip_conntrack_expect",
					sizeof(struct ip_conntrack_expect),
					0, SLAB_HWCACHE_ALIGN, NULL, NULL);
	if (!ip_conntrack_expect_cachep) {
		printk(KERN_ERR "Unable to create ip_expect slab cache\n");
		goto err_free_conntrack_slab;
	}

	/* Don't NEED lock here, but good form anyway. */
	WRITE_LOCK(&ip_conntrack_lock);
	for (i = 0; i < MAX_IP_CT_PROTO; i++)
		ip_ct_protos[i] = &ip_conntrack_generic_protocol;
	/* Sew in builtin protocols. */
	ip_ct_protos[IPPROTO_TCP] = &ip_conntrack_protocol_tcp;
	ip_ct_protos[IPPROTO_UDP] = &ip_conntrack_protocol_udp;
	ip_ct_protos[IPPROTO_ICMP] = &ip_conntrack_protocol_icmp;
	WRITE_UNLOCK(&ip_conntrack_lock);

	for (i = 0; i < ip_conntrack_htable_size; i++)
		INIT_LIST_HEAD(&ip_conntrack_hash[i]);

	/* For use by ipt_REJECT */
	ip_ct_attach = ip_conntrack_attach;

	/* Set up fake conntrack:
	    - to never be deleted, not in any hashes */
	atomic_set(&ip_conntrack_untracked.ct_general.use, 1);
	/*  - and look it like as a confirmed connection */
	set_bit(IPS_CONFIRMED_BIT, &ip_conntrack_untracked.status);

	return ret;

err_free_conntrack_slab:
	kmem_cache_destroy(ip_conntrack_cachep);
err_free_hash:
	vfree(ip_conntrack_hash);
err_unreg_sockopt:
	nf_unregister_sockopt(&so_getorigdst);

	return -ENOMEM;
}